Skip to content

Home

Jump to bottom
Raul Montoya Cardenas edited this page Jul 29, 2026 · 3 revisions

engram-parser

Wiki hero

Generated with Grok Build: Grok 4.5 · xAI Imagine (/imagine)

Pure-Rust, zero-dependency GGUF deserializer and MoE per-expert weight extractor.

Version: 0.1.0 | Edition: 2024 | MSRV: 1.87 | License: MIT OR Apache-2.0

An engram is a physical trace of memory. This crate rips frozen weights (memories) out of MoE GGUF checkpoints so live systems can consume raw byte buffers with shape/dtype metadata — no neural-network math.

What It Does

  • Parse GGUF v3 (magic, header, KV metadata, tensor directory) → GgufLayout
  • Enumerate MoE experts: list_experts
  • Extract one expert’s gate / up / down raw bytes: extract_expert
  • Support stacked (ffn_*_exps.weight) and per-expert (ffn_*.E.weight) layouts

What It Does Not Do

  • No matmul, forward, routing, softmax, or default-path dequant
  • No CUDA / GPU / SIMD
  • Zero crate dependencies ([dependencies] is empty)
  • No model-family adapters or full checkpoint routing (see cortex-tensor)

Start Here

Page Description
Getting Started Install, load, extract
Project Structure Modules and tree
Architecture Ownership and non-goals
GGUF Parsing load_gguf, layout, cursor
Tensor and DType Directory entries and types
MoE Extraction stacked vs per-expert
Errors ParserError
Public API Crate surface
Testing Smoke tests
CI and Quality GHA, security, Docker
MSRV 1.87 policy
Ecosystem cortex-tensor, LIM-9
Glossary Terms

Quick Commands

cargo fmt --check
cargo clippy --all-targets --all-features -- -D warnings
cargo build --all-features
cargo test --all-features

License

Dual-licensed under MIT or Apache-2.0 at your option.

Last updated: July 29, 2026 Updated by: Grok Build: Grok 4.5 Package tip reference: 07a5558 (main, through PR #37)

Clone this wiki locally